Time series is a series of numerical data, which have been recorded at different intervals of time. It is a record of changes recorded in variables over a period of time, the study of which throws light on the economic behavior of a certain variable. It has an important and significant place in business and economics. In this chapter we discuss the components of time series and calculation of trend values by different methods.
Components of time series; free-hand method; moving average method; semiaverage method; least square method
There are many factors that change with the passage of time. For example, consumer price index, rate of inflation, the yearly demands of a commodity, balance of trade, annual profit of a firm, etc. In this chapter we consider data that are collected sequentially over time: i.e., time series data. Numerical variables that are calculated, measured, or observed sequentially on a regular chronological basis are called Time Series. Many economists and statisticians have defined time series in different words. Some of them are quoted below:
A time series is a set of statistical observations arranged in chronological order
Morris Hamburg
A time series is a sequence of values of the same variate corresponding to successive points of time.
Werner Z. Hirsch
A time series is a set of statistical data which are collected, recorded or observed over successive increments.
Patterson
The importance of time series is obvious once it is realized that the main problem of business is making forecasts for the future, which cannot be done unless data representing change over a period of time is analyzed.
The time series data are subjected to two kinds of analysis: Descriptive and Inferential. The descriptive analysis uses graphical and numerical techniques. It provides clear understanding of the time series. Forecasts and their measures of reliability are examples of inferential techniques in time series analysis. They are generally focused on the problems of forecasting future values of the time series.
The analysis of time series is useful to economists, scientists, business that persons, etc. It is also found useful in the study of seismology, oceanography, meteorology, etc. The purpose of time series study is to measure chronologically particular variations. Time series analysis helps in understanding the cream in phenomena.
The time series data are always given over specified periods and one value is generally compared with the other. So before the analysis of time series, the data have to be critically examined and adjusted for various factors. Otherwise discrepancies are likely to arise leading to wrong conclusions. Mainly one or more types of adjustments are needed. Normally the types of adjustments incorporated in a time series data are:
1. Calendar Variation: In some cases monthly consumption of an item is compared within a year. The number of days are different in different months, e.g., the number of days in March is 31 and the number of days in April is 30. Therefore some adjustments are made, therefore are should be worry of the type of variable dealing with before implementing the adjustments for calendar variation. Wages should not be adjusted as the salary in India is paid on monthly basis.
2. Price Variation: Production or sales are to be adjusted for price variation by the formula.
where q=Quantity of production or sales in a specified period; v=Sales in terms of money; and p=Price per unit in the reference period.
If this adjustment is not done, rising of prices will lead to the conclusion that production or sales have increased, though in reality it may not be so.
3. Population Changes: Consumption of sugar, food grain, etc., depends on the number of consumers. If there is an increase in population, then there will be increase of consumption. Similarly demand is also directly related to the population.
If the demand doubles and population also doubles, it should not be that demand has increased.
4. Miscellaneous Changes: We observe that many changes occur with the lapse of time. Synthetic fiber cloth that is more durable is now produced in our country. Some years ago synthetic fiber was not available in our country. We know that units of measurement have also changed. Earlier it was yards and miles, now it is meter and kilometer. Therefore for comparison of two time series, they should be converted to the same unit of measurement.
There are four components of a time series, namely
The components are also called the elements of a time series.
1. Secular trend (or Trend)(Tt): The secular trend also known as long-term trend means long-term movement. It is denoted by Tt (or by T). The population, production, sales, etc., have an increasing or decreasing tendency over periods of time, secular trend measures long-term changes occurring in a time series without bothering about short-term fluctuations occurring in between. If you want to characterize the secular trend of the production of two-wheelers since 1970. You would show Tt as an upward-moving time series over the period from 1970 to the present. This does not imply that the two-wheeler production series has always moved upward from month to month and from year to year, but it does mean the long-term trend has been an increasing one over that period of time. Thus the secular trend is concerned with regular growth or decline.
2. Seasonal variation (St): The seasonal variation describes the fluctuations in the time series that recur during specific time periods. It is denoted by St (or S) For instance certain items have tremendous sale during festivals only in a particular month; rain coats are sold in rainy season; soft drinks and ice cream in summer. All such variations in time series comes under seasonal variation.
3. Cyclic variation (Ct): Cyclic variation relates to periodic changes, cycles related to business are termed as business cycles (or trade cycles). A business normally exceeds a year in length. The changes that occur for periods more than 1 year come under the category of cyclic variations. These cycles are never regular in periodicity and amplitude. Hardly any time series has strict cycles. A large number of factors are responsible for the occurrence of cycles. The changes in social customs, like and dislikes of people, new scientific and technological developments, etc., are some factors responsible for creation of cycles. Cyclic variation is denoted by the symbol Ct (or by C).
4. Irregular variations (It): These variations are due to famines, strikes, wars, droughts, earthquakes, and other calamities. These variations are also called residual variations.
A Mathematical model is used to describe a time series. The objective of a mathematical model is to produce accurate forecasts of future values of the time series. Many different algebraic representations of time series models have been proposed. If Yt denotes any particular observation at time t, then the multiplicative model is of the form:
or
and the additive model is of the form
or
The multiplicative model does not assume the independence of the four components T, S, C, and I of the time series, but the additive model is based on the assumption that four components are independent of each other. We can also use mixed models. Some of the examples of mixed models are given below:
The idea of measuring the trend is to estimate the average growth or decline. The precondition for the measurement of secular trend is that the data must be available for a long period. Otherwise it will not be possible to isolate and estimate the growth or decline in the trend. The following methods are used for measuring the trend:
The free-hand method is the simplest method of ascertaining trend. On the graph paper, time t is measured horizontally, whereas the values of the variable y are measured vertically. The points (t1, y1), (t2, y2), …, (tn, yn) are plotted on a graph paper by taking ti on the x-axis and yi on the y-axis. The plotted points are then joined by straight lines and the trend line is fitted with the help of a transparent ruler or a smooth curve by hand. The trend line is drawn in such way that the following are satisfied as far as possible:
1. The algebraic sum of the deviations of actual values from the trend values are zero.
2. The sum of the squares of the deviations of actual values from the trend values is least.
A free-hand curve removes the short-term variations and exhibits a general trend. Free-hand method is one of the simplest and most flexible methods and sometimes yield good results. It is too subjective. In this method the trend line varies from person to person, as it depends on individual’s judgment. Hence it cannot be used as a basis of prediction.
Example: Fit a straight line trend to the following data by using free-hand graph method:
Years | 1970 | 1971 | 1972 | 1973 | 1974 | 1975 | 1976 |
Profit of the firm X20 (in lakhs of Rs.) | 20 | 30 | 25 | 40 | 45 | 30 | 55 |
In this method the series is divided into two halves. Then the average is found out for each half of the series. The average values are plotted on the graph paper against the mid periods of the corresponding each half series. The line joining these two plotted points gives the trend line. The direction of the line indicates about rising, falling, or constant trend of business movements.
If the number of years in a series is odd, the middle year is excluded at the time of dividing the series into two halves, and then either excluded in both series or excluded totally depending on whether the leftover series contains an even or odd number of years respectively.
The semiaverage method is not subjective and for one series, there is only one trend line. But it is affected by extreme values. This method does not ensure elimination of short-term and cyclic variations. Semiaverage method is superior to free-hand method. It may be used when the data are given for a longer period.
Example 12.1: Fit a straight line trend by using the following data:
Years | 1981 | 1982 | 1983 | 1984 | 1985 | 1986 | 1987 |
Profit (in lakhs of Rs.) | 20 | 22 | 27 | 26 | 30 | 29 | 40 |
Use semiaverage method. Also estimate the profit for the year 1988.
Solution: Trend line by semiaverage method number of years is 7, i.e., odd. We leave the middle most value, i.e., the value corresponding to the year 1984.
Plot 23 against 1982 and 33 against 1986. Join these points as shown in figure below.
The profit in the year 1988 is Rs. 37 lakhs.
Example 12.2: Draw the trend by semiaverage method from the following data:
Year | 1800 | 1810 | 1820 | 1830 | 1840 | 1850 | 1860 |
Price (Index No.) | 129 | 131 | 106 | 91 | 95 | 84 | 93 |
Year | 1870 | 1880 | 1890 | 1900 | 1910 | 1920 | 1930 |
Price (Index No.) | 135 | 100 | 82 | 82 | 103 | 226 | 126 |
Solution: The data correspond to 14 years
We break the data into two equal parts of 7 years each.
First part (first half) | Ordinate to be plotted | Second part (last half) | Ordinate to be plotted | ||
Year | Index No. | Year | Index No. | ||
1800 | 129 | Middle year=104 | 1870 | 135 | Middle year=122 |
1810 | 131 | 1880 | 100 | ||
1820 | 106 | 1890 | 82 | ||
1830 | 91 | 1900 | 82 | ||
1840 | 95 | 1910 | 103 | ||
1850 | 84 | 1920 | 226 | ||
1860 | 93 | 1930 | 126 | ||
729 | 854 |
Plot 104 against 1830 and 122 against 1900. Join these points (Fig. 12.1).
The moving average method is an improvement over the semiaverage method and short-term fluctuations are eliminated by it. A moving average is defined as an average of fixed number of items in the time series which move through the series by dropping the top items of the previous averaged group and adding the next in each successive average.
Let (t1, y1), (t2, y2), …, (tn, yn) denote given time series y1, y2, …, yn are the values of the variable y; corresponding to time periods t1, t2, …, tn, respectively.
The moving averages of order m are defined as
Here y1+y2+…+ym, y2+y3+…+ym+1,… are called moving totals of m.
In using moving averages in estimating the trend, we shall have to decide as what should be the order of the moving averages. The order of the moving average should be equal to the length of the cycles in the time series. In case the order of the moving averages is given in the problem itself, then we shall use that order for computing the moving average. The order of the moving averages may either be odd or even.
The moving averages of order 3 are
These moving averages are called the trend values. They are considered to correspond 2nd, 3rd, …, (n−1)th years, respectively. Calculation of trend values by using moving averages of even order is slightly complicated. The following steps are involved in the method:
Step 1: In the first step, a group of beginning years (periods), which constitute cycle is chosen for calculating the average. This average is placed in front of the mid-year of the group.
Step 2: Now delete the first year value from the group and add a succeeding year value in the group. Find the average of the reconstituted group and place it in front of this group.
Step 3: If the number of years in a group is odd, middle year is located without any problem. But if the number of years in the group is even, the average of the averages in pairs is calculated and placed against the mid-year of the two.
Step 4: Repeat the Step 2 till all years of the data are exhausted.
Step 5: The moving averages calculated are considered as an artificially constructed time series.
Step 6: Plot the moving averages on a graph paper taking years along x-axis and moving averages along y-axis by choosing a proper scale.
Step 7: Join the plotted point in the sequence of time periods. The resulting graph provides the trend.
1. The moving average method eliminates the short-term fluctuations.
2. It reduces the effect of extreme values.
3. As the free-hand method, this method is not subject to personal prejudice and bias of the estimator.
1. Moving average method is not fully mathematical.
2. If the series given is a very large one, then the calculation of moving average is cumbersome.
3. The choice of the period of moving average needs a great amount of care. If an inappropriate period is selected, a true picture of the trend cannot be obtained.
Example 12.3: Estimate the trend values using the data given below by taking a 3-yearly moving averages.
Year | 1980 | 1981 | 1982 | 1983 | 1984 | 1985 | 1986 | 1987 | 1988 |
Sales (in lakhs of units) | 65 | 95 | 80 | 115 | 105 | 135 | 125 | 150 | 140 |
Solution: Trend by 3-yearly moving averages
Year | Sales (in lakhs of units) | 3-year moving totals | 3-year moving averages |
1980 | 65 | – | – |
1981 | 95 | 65+95+80=240 | 240/3=80 |
1982 | 80 | 95+80+115=290 | 290/3=96.67 |
1983 | 115 | 80+115+105=300 | 300/3=100 |
1984 | 105 | 115+105+135=355 | 355/3=118 |
1985 | 135 | 105+135+125=365 | 365/3=121.67 |
1986 | 125 | 135+125+150=410 | 410/3=136.67 |
1987 | 150 | 125+150+140=415 | 415/3=138.33 |
1988 | 140 | – | – |
Example 12.4: Estimate the trend values using the data given below by taking a 4-yearly moving averages:
Year | Value | Year | Values |
1969 | 4 | 1975 | 24 |
1970 | 7 | 1976 | 36 |
1971 | 20 | 1977 | 25 |
1972 | 15 | 1978 | 40 |
1973 | 30 | 1979 | 42 |
1974 | 28 | 1980 | 45 |
Solution: We use a process called “centering of moving averages.” In this method we first calculate 4-yearly moving averages. The first and second 4-year moving averages are added and the total is divided by two and written opposite the gap between the first two 4-year moving averages. The second and third 4-year moving averages are added and the total is divided by two. In short, 2-year moving averages of the 4-year moving averages are calculated. The 2-year moving averages of the 4-year moving averages are called the central 4-year moving averages.
The following table given the centered 4-year moving averages:
Year | Value | 4-yearly moving totals | 4-yearly moving averages | 4-yearly centered moving averages |
1969 | 4 | |||
1970 | 7 | 46 | 11.5 | 14.75 |
1971 | 20 | 72 | 18.0 | 20.625 |
1972 | 15 | 93 | 23.25 | 23.75 |
1973 | 30 | 97 | 24.25 | 26.875 |
1974 | 28 | 118 | 29.5 | 28.875 |
1975 | 24 | 113 | 28.25 | 29.75 |
1976 | 36 | 125 | 31.25 | 33.50 |
1977 | 25 | 143 | 35.75 | 36.875 |
1978 | 40 | 152 | 38 | |
1979 | 42 | |||
1980 | 45 |
Example 12.5: Compute 7 years’ moving averages.
Year | Values | Year | Values | Year | Values |
1954 | 496 | 1959 | 1081 | 1964 | 1442 |
1955 | 615 | 1960 | 1132 | 1965 | 1617 |
1956 | 686 | 1961 | 1139 | 1966 | 1678 |
1957 | 835 | 1962 | 1320 | ||
1958 | 888 | 1963 | 1389 |
Solution: See Table 12.1.
Table 12.1
Year | Value | 7-year moving totals | 7-year moving averages |
1954 | 496 | – | – |
1955 | 615 | – | – |
1956 | 686 | 5733 | – |
1957 | 835 | 6376 | 819.00 |
1958 | 888 | 7081 | 910.85 |
1959 | 1081 | 7784 | 1011.60 |
1960 | 1132 | 8391 | 1112.00 |
1961 | 1139 | 9120 | 1198.70 |
1962 | 1320 | 9717 | 1303 |
1963 | 1389 | – | 1388 |
1964 | 1442 | – | – |
1965 | 1617 | – | – |
1966 | 1678 | – | – |
The method of least squares is a widely used method of fitting curve for a given data. It is the most popular method used to determine the position of the trend line of a given time series. The trend line is technically called the best fit. In this method a mathematical relationship is established between the time factor and the variable given. Let (t1, y1), (t2, y2), …, (tn, yn) denote the given time series. In this method the trend value yc of the variable y are computed so as to satisfy the conditions:
1. The sum of the deviations of y from their corresponding trend values is zero.
i.e.,
2. The sum of the square of the deviations of the values of y from their corresponding trend values is the least.
i.e.,
is least.
The equation of the trend line can be expressed as
where a and b are constants and the trend line satisfies the conditions:
The values of a and b determined such that they satisfy the equations.
(12.1)
(12.2)
Eqs. (12.1) and (12.3) are called normal equations.
Solving Eqs. (12.1) and (12.2) we get
and
In the equation, yc=a+bx, of the trend, a represents the trend of the variable when x=0 and b represents the slope of the trend line. If b is positive, the trend line will be upward and if b is negative the trend line will be downward.
When the origin is mentioned and the deviations from the origin is denoted by x, we get
(The sum of derivation from the origin=).
Note: If n is odd, we take the middle value (Middle year) as the origin. If n is even, there will be two middle values. In this case we take the mean of the two middle values as the origin.
1. The method is mathematically sound.
2. The estimates a and b are unbiased.
3. The least square method gives trend values for all the years and the method is devoid of all kinds of subjectivity.
4. The algebraic sum of deviations of actual values from trend values is zero and the sum of the deviations is minimum.
1. The least square method is highly mathematical, therefore, it is difficult for a layman to understand it.
2. The method is not flexible. If certain new values are included in the given, time series, the values of n, , , and would change. Which affects the trend values.
3. It has been assumed that y is only a linear function of time period x. Which may not be true in many situations.
Example 12.6: Find the least square line y=a+bx for the data:
x | –2 | –1 | 0 | 1 | 2 |
y | 1 | 2 | 3 | 3 | 4 |
Solution:
x | y | x2 | xy |
–2 | 1 | 4 | –2 |
–1 | 2 | 1 | –2 |
0 | 3 | 0 | 0 |
1 | 3 | 1 | 3 |
2 | 4 | 4 | 8 |
∴ , , , , and x=5
The normal equations are
Putting the values of n, in the above equation, we get
(12.3)
(12.4)
From Eqs. (12.3) and (12.4) we get
The required of least square line is
Example 12.7: Fit a straight line trend by the method of least square from the following data and find the trend values.
Year | 1958 | 1959 | 1960 | 1961 | 1962 |
Sales (in lakhs of units) | 65 | 95 | 80 | 115 | 105 |
Solution: We have n=5
∴ n is odd.
Taking middle year, i.e., 1960 as the origin. We get,
Year | Sales | x | x2 | xy |
1958 | 65 | –2 | 4 | –130 |
1959 | 95 | –1 | 1 | –95 |
1960 | 80 | 0 | 0 | 0 |
1961 | 115 | 1 | 1 | 115 |
1962 | 105 | 2 | 4 | 210 |
Total |
∴ n=5, , , , and
∴ The equation of the straight line trend is
For the year 1958, x=–2
For the year 1959, x=–1
For the year 1960, x=0
For the year 1961, x=1
For the year 1962, x=2
We have
Year | Trend value |
1958 | 72 |
1959 | 82 |
1960 | 92 |
1961 | 102 |
1962 | 112 |
and the straight line trend is yc=92+10x or simply y=92+10x.
Example 12.8: Determine the trend by the method of least squares. Also find the trend values.
Year | 1950 | 1951 | 1952 | 1953 | 1954 | 1955 | 1956 | 1957 |
Value | 346 | 411 | 392 | 512 | 626 | 640 | 611 | 796 |
Solution: Here n=9
∴ n is even.
1953 and 1954 are the middle years.
The origin is
We take x=year−1953.5
Year | x | y | x2 | xy |
1950 | –3.5 | 346 | 12.25 | –1211.00 |
1951 | –2.5 | 411 | 6.25 | –1027.50 |
1952 | –1.5 | 392 | 2.25 | –588.00 |
1953 | –0.5 | 512 | 0.25 | –256.00 |
1954 | 0.5 | 626 | 0.25 | 313.00 |
1955 | 1.5 | 640 | 2.25 | 960.00 |
1956 | 2.5 | 611 | 6.25 | 1527.50 |
1957 | 3.5 | 796 | 12.25 | 2786.00 |
Total | 0 | 4334 | 42.00 | 2504.00 |
∴ We have n=8, , and
∴ The equation of the trend line is
The trend values are:
Year | x | Trend: y=541.75+(59.60)x |
1950 | –3.5 | 333.15 |
1951 | –2.5 | 392.75 |
1952 | –1.5 | 452.35 |
1953 | –0.5 | 511.95 |
1954 | 0.5 | 571.95 |
1955 | 1.5 | 631.15 |
1956 | 2.5 | 690.75 |
1957 | 3.5 | 750.35 |
So far the discussion about trend is confined mostly to the linear trend. There are situations where linear trend is not found suitable. For instance consider the population growth. In the beginning of a period population growth will be slow but will start to multiply at a faster rate, in the later period. For such a type of time series data, a nonlinear trend would depict a better trend than the linear one. Some well-known methods of determining nonlinear trends are:
The above methods have been discussed in this chapter. If the trend is changing frequently, a curve will give a picture of trend. Which curve is best suited to the data may be guessed by plotting time series data on a graph. When the shape of the curve is known, the mathematical equation for it may be given. Once the equation is decided, it can be fitted to the available time series data. Some of the frequently used curve are:
We shall restrict ourselves only to the study of parabolic curves.
Parabola: The parabolic curve is mathematically represented by a second-degree polynomial of the form
It can be fitted by the method of least square, using the method of least squares we get the three normal equations.
Solving the above equations we obtain the values for a, b, and c.
Substituting the values of a, b, and c is
We get the parabola. The curve is a quadratic curve and is also known as a response curve. The shape of the curve depends on the values of b and c. Its geometric shapes are as shown in Fig. 12.1 (Fig. 12.2).
Example 12.9: The prices to the commodities during 1978–83 are given below. Fit a parabola y=a+bx+cx2 to the data. Estimate the price of the commodity for the year 1984.
Year | 1978 | 1979 | 1980 | 1981 | 1982 | 1983 |
Price | 100 | 107 | 128 | 140 | 181 | 192 |
Also find the trend values.
Trend by least square method.
S. No. | Year | y | x | x2 | x3 | x4 | xy | x2y |
1. | 1978 | 100 | –5 | 25 | –125 | 625 | –500 | 2500 |
2. | 1979 | 107 | –3 | 9 | –27 | 81 | –321 | 963 |
3. | 1980 | 128 | –1 | 1 | –1 | 1 | –128 | 128 |
4. | 1981 | 140 | 1 | 1 | 1 | 1 | 140 | 140 |
5. | 1982 | 181 | 3 | 9 | 27 | 81 | 543 | 1629 |
6. | 1983 | 192 | 5 | 25 | 125 | 625 | 960 | 4800 |
The normal equation are
i.e.,
(12.5)
(12.6)
(12.7)
From Eq. (12.6) we get
Consider Eqs. (12.5) and (12.7)
(12.8)
From Eq. (12.7)
where 1980.5 is the origin and x unit is years.
Year | x | Trend value |
1978 | –5 | 136.13+9.914 (–5)+0.446 (25)=97.710 |
1976 | –3 | 136.13+9.914 (–3)+0.446 (9)=110.402 |
1980 | –1 | 136.13+9.914 (–1)+0.446 (1)=126.662 |
1981 | 1 | 136.13+9.914 (1)+0.446 (1)=146.990 |
1982 | 3 | 136.13+9.914 (3)+0.446 (9)=169.886 |
1983 | 5 | 136.13+9.914 (5)+0.446 (25)=196.85 |
Estimated value of price for the year 1984:
We have x=(1984−1980.5) × 2=7
Estimated price for the year 1984:
A time series has three characteristics namely
We can shift the origin and change the trend equation or we can change unit of variable to find the new trend equation. In this section we discuss the following conversions:
1. Conversion of the origin: Let yc=f(x) the equation of the trend where x denotes the deviations of time periods from the origin and y denotes the variables of the time series. If the origin is shifted by k periods forward, then the new trend equation is of the form
If the origin is shifted back by k periods then the new trend equation is of the form
(where k>0)
Example 12.10: The parabolic trend of the equation of a time series is given by
with origin=1980, and x unit=1 year shift the origin to (a) 1984, (b) 1979 and find the new trend equations.
Solution: We have
The origin under reference=1980
a. When the origin is shifted to 1984, x is to be replaced by x+(1984−1980)=x+4 in the given equation.
i.e.,
The new trend equation with new origin at 1984 is
The new trend equation with new origin at 1984 is
2. Conversion of trend values: Usually trend is computed from figures. If it is required to compute monthly trend, it is more convenient to compute the trend equation from the annual data and then convert it to a monthly trend. To convert a trend equation operative on annual level to a monthly level, we divide the constant a by 12 and the constant b by 144 (i.e., b is divided twice by 12).
Let
with
If we convert the trend equation, so that x unit is 1 month and y unit is monthly average then the equation of new trend line will be
i.e.,
If the annual trend equation yc=a+bx is converted to half yearly trend equation, then the new trend equation will be of the form
If the annual trend equation is converted into quarterly trend equation, then it is of the form
where x unit: one quarter; y unit: quarterly values.
Example 12.11: Convert the following annual trend equation for cloth production in a factory to a monthly trend equation.
(origin 1976, time limit 1 year, y=cloth production in ′000 m).
Solution: Annual trend equation is y=108+7.2x
∴ Monthly trend equation is
Note: When the data are given monthly averages per year, the value of a remains unchanged in the conversion process, in which case we take new trend lines as
Example 12.12: Convert the following annual trend equation of ABC corporation to a monthly level: y=41+7.2x (Origin: 1976, x units are year, y=average monthly sales).
Solution: y is average monthly sales.
∴ The monthly trend equation can be written as
(Origin July 1, 1976, time unit 1 month, y=monthly cloth production in ′000 m).
Example 12.13: The parabolic trend equation of a time series is given by yc=5+x−x2 with origin 1980, and x limit=1 year, y=annual production. Convert the trend equation so that
Solution: The trend equation is yc=5+x−x2 with origin 1980, x unit=1 year, and y unit=annual production.
The new trend equation is
i.e.,
2. What is meant by cyclic variation?
3. Give various adjustments usually practiced during editing of data meant for analysis of time series.
4. Discuss irregular variation in the context of time series.
5. What is semiaverage method?
6. What are the merits and demerits of semiaverage method?
7. Draw free-hand trend from the following time series:
Year | 1957–58 | 1958–59 | 1959–60 | 1960–61 | 1961–62 | 1962–63 | 1963–64 |
Reserves | 612 | 719 | 820 | 907 | 1001 | 1106 | 1231 |
8. Draw a free-hand trend for the following series:
Year | 1956 | 1957 | 1958 | 1959 | 1960 | 1961 | 1962 | 1963 | 1964 | 1965 |
Yield of wheat (Million tons) | 12.8 | 13.9 | 12.8 | 13.9 | 13.4 | 6.5 | 29 | 14.8 | 14.9 | 15.9 |
9. Fit a straight line trend to the following data, using free-hand graph method:
Year | 1980 | 1981 | 1982 | 1983 | 1984 | 1985 | 1986 |
Profit (in lakhs of Rs.) | 20 | 30 | 25 | 40 | 42 | 30 | 50 |
10. Calculate 3-year moving averages for the following data:
Year | 1970 | 1971 | 1972 | 1973 | 1974 | 1975 | 1976 | 1977 | 1978 |
Profit (in Lakhs of Rs.) | 45 | 80 | 70 | 110 | 100 | 125 | 115 | 140 | 130 |
11. Compute trend by moving average method assuming “a four year cycle.”
Year | Sales | Year | Sales |
1984 | 75 | 1990 | 70 |
1985 | 60 | 1991 | 75 |
1986 | 55 | 1992 | 85 |
1987 | 60 | 1993 | 100 |
1988 | 65 | 1994 | 70 |
1989 | 70 |
12. The following table gives the number of workers employed in a small industry during 1980–89. Calculate the trend values by using 3-yearly moving averages.
Year | No. of workers | Year | No. of workers |
1980 | 20 | 1984 | 27 |
1981 | 24 | 1985 | 26 |
1982 | 25 | 1986 | 28 |
1983 | 18 | 1987 | 30 |
13. Below are given figures of production (in thousand pounds) of a sugar factory.
Year | 1981 | 1982 | 1983 | 1984 | 1985 | 1986 | 1987 |
Production | 80 | 90 | 92 | 83 | 94 | 99 | 92 |
Find the trend by least squares method?
14. Find out the straight line trend and trend values by the method of least squares for the following data. Also find out the expected value of the year 1938.
Year | 1929 | 1930 | 1931 | 1932 | 1933 | 1934 |
No. of industrial failures | 23 | 26 | 28 | 32 | 20 | 12 |
Ans: yc=21.857–2.46x, y1938=7.097.
15. Draw trend by semiaverage method.
Year | 1944 | 1945 | 1946 | 1947 | 1948 | 1949 |
Value | 16 | 18 | 25.3 | 35.3 | 46.6 | 53.2 |
Year | 1950 | 1951 | 1952 | 1953 | 1954 | 1955 |
Value | 4.6 | 50.9 | 53.6 | 84.5 | 70 | 79 |
Year | 1956 | 1957 | 1958 | 1959 | 1960 | 1961 |
Value | 89.5 | 97.5 | 105.92 | 119 | 119.62 | 114.5 |
16. The production of pig iron and ferro-alloys in thousand metric tons in India is given below:
Year (x) | Production (′000 M tons) | Year (x) | Production (′000 M tons) |
1974 | 620 | 1979 | 745 |
1975 | 713 | 1980 | 726 |
1976 | 833 | 1981 | 806 |
1977 | 835 | 1982 | 861 |
1978 | 810 |
Find the trend time y=a+bx, by the method of least squares?
17. Fit a straight line of the form y=mx+c for the following time series showing production of a commodity over a period of 8 years.
Year | Production (in lakhs) | Year | Production (in lakhs) |
1961 | 8 | 1965 | 20 |
1962 | 12 | 1966 | 23 |
1963 | 15 | 1967 | 27 |
1964 | 18 | 1968 | 30 |
18. Compute 5-year moving averages.
Year | 1950 | 1951 | 1952 | 1953 | 1954 | 1955 |
Value | 901 | 95.3 | 99.7 | 98.2 | 104.8 | 96.1 |
Year | 1956 | 1957 | 1958 | 1959 | 1960 | 1961 |
Value | 99.8 | 113.1 | 113.9 | 126.0 | 128.4 | 141.4 |
Year | 1962 | 1963 | 1964 | 1965 | 1966 | 1967 |
Value | 148.0 | 154.0 | 172.1 | 204.3 | 203.4 | 231.2 |
Ans: 87.6, 98.8, 99.7, 102.4, 105.5, 109.8, 116.2, 124.6, 131.5, 139.6, 148.8, 164.0, 176.4, 193.0
19. Compute 5-years moving average.
Year | 1 | 2 | 3 | 4 | 5 | 6 | 7 |
Value | 328 | 317 | 357 | 392 | 402 | 405 | 410 |
Year | 8 | 9 | 10 | 11 | 12 | 13 | 14 |
Value | 427 | 405 | 438 | 445 | 447 | 480 | 482 |
Ans: 359.2, 374.6, 393.2, 407.2, 409.8, 417, 425, 432.4, 443, 458.4
20. Compute the trend from the following data by the method of least squares:
Year | 1970 | 1971 | 1972 | 1973 | 1974 |
Population (in lakhs) | 830 | 920 | 710 | 900 | 1690 |
21. Obtain the trend of bank clearances by the method of moving averages (assume a 5-yearly cycle).
Year | Bank clearance (in lakhs of Rs.) | Year | Bank clearance (in lakhs of Rs.) |
1951 | 53 | 1957 | 105 |
1952 | 79 | 1958 | 87 |
1953 | 76 | 1959 | 79 |
1954 | 66 | 1960 | 104 |
1955 | 69 | 1961 | 97 |
1956 | 74 | 1962 | 92 |
Ans: 68.6, 76.8, 82, 84.2, 86.8, 93.8, 94.4, 91.8
22. Below are the given figures of production (in thousand tons) of a sugar factory:
Year | 1966 | 1967 | 1968 | 1969 | 1970 | 1971 | 1972 |
Production (in thousand tons) | 80 | 90 | 92 | 83 | 94 | 99 | 92 |
Find the average production, rate of growth, and trend ordinates (apply least square method)?