Consider the following statements: 

(a) Mode can be computed from histogram.

(b) Median is not independent of change of scale.

(c) Variance is independent of change of origin and scale.

Analysis of Statement a: Mode can be computed from a histogram.

This statement is correct. A histogram represents the distribution of grouped continuous data. The highest bar in a histogram corresponds to the modal class, which contains the maximum frequency. The exact mode can be calculated graphically by drawing intersecting lines inside this highest bar to the adjacent bars.

Analysis of Statement b: Median is not independent of change of scale.

This statement is correct. A change of scale means multiplying or dividing each data point by a constant value. Let the original dataset be given by:

$$ X $$

If the dataset is multiplied by a non-zero constant scale factor $$ k $$, the new scaled dataset is:

$$ Y = kX $$

The median of this new dataset changes proportionally to the scale factor:

$$ \text{Median}(Y) = k \cdot \text{Median}(X) $$

Since the median value changes when the scale is altered, it is dependent on the change of scale. Therefore, it is not independent of a change of scale.

Analysis of Statement c: Variance is independent of change of origin and scale.

This statement is incorrect. While variance is independent of a change of origin, it is dependent on a change of scale. Let the original data observations be transformed by a change of origin $$ a $$ and a change of scale $$ b $$:

$$ Y = bX + a $$

The variance of the transformed dataset relates to the original variance by the square of the scale factor:

$$ \text{Variance}(Y) = b^2 \cdot \text{Variance}(X) $$

Adding or subtracting a constant value $$ a $$ shifts the data points uniformly and does not alter the overall spread around the mean. However, multiplying the data points by a factor $$ b $$ scales the distance between values. This dependency causes the variance to be modified by $$ b^2 $$.

Final Answer:

Only statements (a) and (b) are correct.